skills/moshe-ship/mkhlab/khalas/Gen Agent Trust Hub

khalas

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local binary named khalas to perform token analysis and optimization tasks through shell commands.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by processing untrusted user data in shell arguments.
  • Ingestion points: User-provided text is passed directly as arguments to the khalas tool in SKILL.md.
  • Boundary markers: The documentation uses double quotes for input wrapping, which is a weak boundary against sophisticated shell injection.
  • Capability inventory: Performs shell execution with variable user-controlled input.
  • Sanitization: No input validation, escaping, or filtering is specified for the text before it is passed to the command line.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 01:16 PM
Security Audit — agent-trust-hub — khalas